{
  "best_metric": 0.8675475120544434,
  "best_model_checkpoint": "./lora-out/checkpoint-60",
  "epoch": 93.33333333333333,
  "eval_steps": 10,
  "global_step": 140,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "learning_rate": 2e-05,
      "loss": 1.9263,
      "step": 1
    },
    {
      "epoch": 1.33,
      "learning_rate": 4e-05,
      "loss": 0.6362,
      "step": 2
    },
    {
      "epoch": 2.0,
      "learning_rate": 6e-05,
      "loss": 1.2827,
      "step": 3
    },
    {
      "epoch": 2.67,
      "learning_rate": 8e-05,
      "loss": 1.271,
      "step": 4
    },
    {
      "epoch": 3.0,
      "learning_rate": 0.0001,
      "loss": 0.634,
      "step": 5
    },
    {
      "epoch": 4.0,
      "learning_rate": 0.00012,
      "loss": 1.8734,
      "step": 6
    },
    {
      "epoch": 5.0,
      "learning_rate": 0.00014,
      "loss": 1.815,
      "step": 7
    },
    {
      "epoch": 5.33,
      "learning_rate": 0.00016,
      "loss": 0.5571,
      "step": 8
    },
    {
      "epoch": 6.0,
      "learning_rate": 0.00018,
      "loss": 1.0428,
      "step": 9
    },
    {
      "epoch": 6.67,
      "learning_rate": 0.0002,
      "loss": 0.953,
      "step": 10
    },
    {
      "epoch": 6.67,
      "eval_loss": 1.6378157138824463,
      "eval_runtime": 0.8713,
      "eval_samples_per_second": 6.886,
      "eval_steps_per_second": 3.443,
      "step": 10
    },
    {
      "epoch": 7.0,
      "learning_rate": 0.00019997482349425066,
      "loss": 0.4287,
      "step": 11
    },
    {
      "epoch": 8.0,
      "learning_rate": 0.00019989930665413147,
      "loss": 1.2133,
      "step": 12
    },
    {
      "epoch": 9.0,
      "learning_rate": 0.0001997734875046456,
      "loss": 1.1351,
      "step": 13
    },
    {
      "epoch": 9.33,
      "learning_rate": 0.00019959742939952392,
      "loss": 0.355,
      "step": 14
    },
    {
      "epoch": 10.0,
      "learning_rate": 0.00019937122098932428,
      "loss": 0.68,
      "step": 15
    },
    {
      "epoch": 10.67,
      "learning_rate": 0.00019909497617679348,
      "loss": 0.6661,
      "step": 16
    },
    {
      "epoch": 11.0,
      "learning_rate": 0.00019876883405951377,
      "loss": 0.3162,
      "step": 17
    },
    {
      "epoch": 12.0,
      "learning_rate": 0.00019839295885986296,
      "loss": 0.9141,
      "step": 18
    },
    {
      "epoch": 13.0,
      "learning_rate": 0.00019796753984232358,
      "loss": 0.8809,
      "step": 19
    },
    {
      "epoch": 13.33,
      "learning_rate": 0.00019749279121818235,
      "loss": 0.2831,
      "step": 20
    },
    {
      "epoch": 13.33,
      "eval_loss": 1.0763869285583496,
      "eval_runtime": 0.8722,
      "eval_samples_per_second": 6.879,
      "eval_steps_per_second": 3.44,
      "step": 20
    },
    {
      "epoch": 14.0,
      "learning_rate": 0.0001969689520376687,
      "loss": 0.5415,
      "step": 21
    },
    {
      "epoch": 14.67,
      "learning_rate": 0.00019639628606958533,
      "loss": 0.5414,
      "step": 22
    },
    {
      "epoch": 15.0,
      "learning_rate": 0.00019577508166849304,
      "loss": 0.2592,
      "step": 23
    },
    {
      "epoch": 16.0,
      "learning_rate": 0.00019510565162951537,
      "loss": 0.7754,
      "step": 24
    },
    {
      "epoch": 17.0,
      "learning_rate": 0.00019438833303083678,
      "loss": 0.7689,
      "step": 25
    },
    {
      "epoch": 17.33,
      "learning_rate": 0.00019362348706397373,
      "loss": 0.2523,
      "step": 26
    },
    {
      "epoch": 18.0,
      "learning_rate": 0.0001928114988519039,
      "loss": 0.5015,
      "step": 27
    },
    {
      "epoch": 18.67,
      "learning_rate": 0.0001919527772551451,
      "loss": 0.5023,
      "step": 28
    },
    {
      "epoch": 19.0,
      "learning_rate": 0.00019104775466588161,
      "loss": 0.2493,
      "step": 29
    },
    {
      "epoch": 20.0,
      "learning_rate": 0.0001900968867902419,
      "loss": 0.74,
      "step": 30
    },
    {
      "epoch": 20.0,
      "eval_loss": 1.0189049243927002,
      "eval_runtime": 0.8726,
      "eval_samples_per_second": 6.876,
      "eval_steps_per_second": 3.438,
      "step": 30
    },
    {
      "epoch": 21.0,
      "learning_rate": 0.0001891006524188368,
      "loss": 0.7203,
      "step": 31
    },
    {
      "epoch": 21.33,
      "learning_rate": 0.0001880595531856738,
      "loss": 0.2385,
      "step": 32
    },
    {
      "epoch": 22.0,
      "learning_rate": 0.00018697411331556956,
      "loss": 0.4841,
      "step": 33
    },
    {
      "epoch": 22.67,
      "learning_rate": 0.00018584487936018661,
      "loss": 0.4746,
      "step": 34
    },
    {
      "epoch": 23.0,
      "learning_rate": 0.00018467241992282843,
      "loss": 0.2257,
      "step": 35
    },
    {
      "epoch": 24.0,
      "learning_rate": 0.00018345732537213027,
      "loss": 0.6933,
      "step": 36
    },
    {
      "epoch": 25.0,
      "learning_rate": 0.00018220020754479102,
      "loss": 0.6819,
      "step": 37
    },
    {
      "epoch": 25.33,
      "learning_rate": 0.00018090169943749476,
      "loss": 0.2184,
      "step": 38
    },
    {
      "epoch": 26.0,
      "learning_rate": 0.00017956245488817812,
      "loss": 0.4415,
      "step": 39
    },
    {
      "epoch": 26.67,
      "learning_rate": 0.000178183148246803,
      "loss": 0.4336,
      "step": 40
    },
    {
      "epoch": 26.67,
      "eval_loss": 0.9619529843330383,
      "eval_runtime": 0.874,
      "eval_samples_per_second": 6.865,
      "eval_steps_per_second": 3.433,
      "step": 40
    },
    {
      "epoch": 27.0,
      "learning_rate": 0.0001767644740358011,
      "loss": 0.2187,
      "step": 41
    },
    {
      "epoch": 28.0,
      "learning_rate": 0.00017530714660036112,
      "loss": 0.642,
      "step": 42
    },
    {
      "epoch": 29.0,
      "learning_rate": 0.00017381189974873407,
      "loss": 0.6302,
      "step": 43
    },
    {
      "epoch": 29.33,
      "learning_rate": 0.00017227948638273916,
      "loss": 0.2054,
      "step": 44
    },
    {
      "epoch": 30.0,
      "learning_rate": 0.00017071067811865476,
      "loss": 0.4056,
      "step": 45
    },
    {
      "epoch": 30.67,
      "learning_rate": 0.00016910626489868649,
      "loss": 0.3933,
      "step": 46
    },
    {
      "epoch": 31.0,
      "learning_rate": 0.00016746705459320745,
      "loss": 0.1891,
      "step": 47
    },
    {
      "epoch": 32.0,
      "learning_rate": 0.00016579387259397127,
      "loss": 0.5689,
      "step": 48
    },
    {
      "epoch": 33.0,
      "learning_rate": 0.0001640875613985024,
      "loss": 0.5574,
      "step": 49
    },
    {
      "epoch": 33.33,
      "learning_rate": 0.00016234898018587337,
      "loss": 0.1827,
      "step": 50
    },
    {
      "epoch": 33.33,
      "eval_loss": 0.8636454939842224,
      "eval_runtime": 0.8737,
      "eval_samples_per_second": 6.867,
      "eval_steps_per_second": 3.434,
      "step": 50
    },
    {
      "epoch": 34.0,
      "learning_rate": 0.000160579004384082,
      "loss": 0.3592,
      "step": 51
    },
    {
      "epoch": 34.67,
      "learning_rate": 0.00015877852522924732,
      "loss": 0.3602,
      "step": 52
    },
    {
      "epoch": 35.0,
      "learning_rate": 0.0001569484493168452,
      "loss": 0.1678,
      "step": 53
    },
    {
      "epoch": 36.0,
      "learning_rate": 0.00015508969814521025,
      "loss": 0.5046,
      "step": 54
    },
    {
      "epoch": 37.0,
      "learning_rate": 0.00015320320765153367,
      "loss": 0.5016,
      "step": 55
    },
    {
      "epoch": 37.33,
      "learning_rate": 0.00015128992774059063,
      "loss": 0.1718,
      "step": 56
    },
    {
      "epoch": 38.0,
      "learning_rate": 0.0001493508218064347,
      "loss": 0.3245,
      "step": 57
    },
    {
      "epoch": 38.67,
      "learning_rate": 0.00014738686624729986,
      "loss": 0.3233,
      "step": 58
    },
    {
      "epoch": 39.0,
      "learning_rate": 0.00014539904997395468,
      "loss": 0.1573,
      "step": 59
    },
    {
      "epoch": 40.0,
      "learning_rate": 0.00014338837391175582,
      "loss": 0.4726,
      "step": 60
    },
    {
      "epoch": 40.0,
      "eval_loss": 0.8675475120544434,
      "eval_runtime": 0.8737,
      "eval_samples_per_second": 6.867,
      "eval_steps_per_second": 3.434,
      "step": 60
    },
    {
      "epoch": 41.0,
      "learning_rate": 0.00014135585049665207,
      "loss": 0.4665,
      "step": 61
    },
    {
      "epoch": 41.33,
      "learning_rate": 0.00013930250316539238,
      "loss": 0.1493,
      "step": 62
    },
    {
      "epoch": 42.0,
      "learning_rate": 0.00013722936584019453,
      "loss": 0.3025,
      "step": 63
    },
    {
      "epoch": 42.67,
      "learning_rate": 0.0001351374824081343,
      "loss": 0.2971,
      "step": 64
    },
    {
      "epoch": 43.0,
      "learning_rate": 0.00013302790619551674,
      "loss": 0.1348,
      "step": 65
    },
    {
      "epoch": 44.0,
      "learning_rate": 0.00013090169943749476,
      "loss": 0.4268,
      "step": 66
    },
    {
      "epoch": 45.0,
      "learning_rate": 0.00012875993274320173,
      "loss": 0.4176,
      "step": 67
    },
    {
      "epoch": 45.33,
      "learning_rate": 0.00012660368455666752,
      "loss": 0.1309,
      "step": 68
    },
    {
      "epoch": 46.0,
      "learning_rate": 0.0001244340406137894,
      "loss": 0.2693,
      "step": 69
    },
    {
      "epoch": 46.67,
      "learning_rate": 0.00012225209339563145,
      "loss": 0.2564,
      "step": 70
    },
    {
      "epoch": 46.67,
      "eval_loss": 0.9176617860794067,
      "eval_runtime": 0.8733,
      "eval_samples_per_second": 6.871,
      "eval_steps_per_second": 3.435,
      "step": 70
    },
    {
      "epoch": 47.0,
      "learning_rate": 0.00012005894157832729,
      "loss": 0.1313,
      "step": 71
    },
    {
      "epoch": 48.0,
      "learning_rate": 0.00011785568947986367,
      "loss": 0.3761,
      "step": 72
    },
    {
      "epoch": 49.0,
      "learning_rate": 0.0001156434465040231,
      "loss": 0.3719,
      "step": 73
    },
    {
      "epoch": 49.33,
      "learning_rate": 0.00011342332658176555,
      "loss": 0.1238,
      "step": 74
    },
    {
      "epoch": 50.0,
      "learning_rate": 0.00011119644761033078,
      "loss": 0.2303,
      "step": 75
    },
    {
      "epoch": 50.67,
      "learning_rate": 0.00010896393089034336,
      "loss": 0.2324,
      "step": 76
    },
    {
      "epoch": 51.0,
      "learning_rate": 0.00010672690056120399,
      "loss": 0.1158,
      "step": 77
    },
    {
      "epoch": 52.0,
      "learning_rate": 0.00010448648303505151,
      "loss": 0.3286,
      "step": 78
    },
    {
      "epoch": 53.0,
      "learning_rate": 0.00010224380642958052,
      "loss": 0.3256,
      "step": 79
    },
    {
      "epoch": 53.33,
      "learning_rate": 0.0001,
      "loss": 0.1031,
      "step": 80
    },
    {
      "epoch": 53.33,
      "eval_loss": 0.9727662205696106,
      "eval_runtime": 0.8715,
      "eval_samples_per_second": 6.884,
      "eval_steps_per_second": 3.442,
      "step": 80
    },
    {
      "epoch": 54.0,
      "learning_rate": 9.775619357041952e-05,
      "loss": 0.2059,
      "step": 81
    },
    {
      "epoch": 54.67,
      "learning_rate": 9.551351696494854e-05,
      "loss": 0.2032,
      "step": 82
    },
    {
      "epoch": 55.0,
      "learning_rate": 9.327309943879604e-05,
      "loss": 0.0924,
      "step": 83
    },
    {
      "epoch": 56.0,
      "learning_rate": 9.103606910965666e-05,
      "loss": 0.2809,
      "step": 84
    },
    {
      "epoch": 57.0,
      "learning_rate": 8.880355238966923e-05,
      "loss": 0.2757,
      "step": 85
    },
    {
      "epoch": 57.33,
      "learning_rate": 8.657667341823448e-05,
      "loss": 0.088,
      "step": 86
    },
    {
      "epoch": 58.0,
      "learning_rate": 8.435655349597689e-05,
      "loss": 0.1725,
      "step": 87
    },
    {
      "epoch": 58.67,
      "learning_rate": 8.214431052013634e-05,
      "loss": 0.1654,
      "step": 88
    },
    {
      "epoch": 59.0,
      "learning_rate": 7.994105842167273e-05,
      "loss": 0.0806,
      "step": 89
    },
    {
      "epoch": 60.0,
      "learning_rate": 7.774790660436858e-05,
      "loss": 0.2316,
      "step": 90
    },
    {
      "epoch": 60.0,
      "eval_loss": 1.0534545183181763,
      "eval_runtime": 0.8706,
      "eval_samples_per_second": 6.892,
      "eval_steps_per_second": 3.446,
      "step": 90
    },
    {
      "epoch": 61.0,
      "learning_rate": 7.556595938621058e-05,
      "loss": 0.2254,
      "step": 91
    },
    {
      "epoch": 61.33,
      "learning_rate": 7.339631544333249e-05,
      "loss": 0.0724,
      "step": 92
    },
    {
      "epoch": 62.0,
      "learning_rate": 7.124006725679828e-05,
      "loss": 0.1469,
      "step": 93
    },
    {
      "epoch": 62.67,
      "learning_rate": 6.909830056250527e-05,
      "loss": 0.1392,
      "step": 94
    },
    {
      "epoch": 63.0,
      "learning_rate": 6.697209380448333e-05,
      "loss": 0.0677,
      "step": 95
    },
    {
      "epoch": 64.0,
      "learning_rate": 6.486251759186572e-05,
      "loss": 0.1941,
      "step": 96
    },
    {
      "epoch": 65.0,
      "learning_rate": 6.277063415980549e-05,
      "loss": 0.1933,
      "step": 97
    },
    {
      "epoch": 65.33,
      "learning_rate": 6.069749683460765e-05,
      "loss": 0.0599,
      "step": 98
    },
    {
      "epoch": 66.0,
      "learning_rate": 5.864414950334796e-05,
      "loss": 0.1258,
      "step": 99
    },
    {
      "epoch": 66.67,
      "learning_rate": 5.6611626088244194e-05,
      "loss": 0.1146,
      "step": 100
    },
    {
      "epoch": 66.67,
      "eval_loss": 1.147660493850708,
      "eval_runtime": 0.8723,
      "eval_samples_per_second": 6.878,
      "eval_steps_per_second": 3.439,
      "step": 100
    },
    {
      "epoch": 67.0,
      "learning_rate": 5.4600950026045326e-05,
      "loss": 0.0585,
      "step": 101
    },
    {
      "epoch": 68.0,
      "learning_rate": 5.261313375270014e-05,
      "loss": 0.1722,
      "step": 102
    },
    {
      "epoch": 69.0,
      "learning_rate": 5.0649178193565314e-05,
      "loss": 0.1656,
      "step": 103
    },
    {
      "epoch": 69.33,
      "learning_rate": 4.87100722594094e-05,
      "loss": 0.0534,
      "step": 104
    },
    {
      "epoch": 70.0,
      "learning_rate": 4.6796792348466356e-05,
      "loss": 0.1112,
      "step": 105
    },
    {
      "epoch": 70.67,
      "learning_rate": 4.491030185478976e-05,
      "loss": 0.107,
      "step": 106
    },
    {
      "epoch": 71.0,
      "learning_rate": 4.305155068315481e-05,
      "loss": 0.0502,
      "step": 107
    },
    {
      "epoch": 72.0,
      "learning_rate": 4.12214747707527e-05,
      "loss": 0.1502,
      "step": 108
    },
    {
      "epoch": 73.0,
      "learning_rate": 3.942099561591802e-05,
      "loss": 0.1472,
      "step": 109
    },
    {
      "epoch": 73.33,
      "learning_rate": 3.7651019814126654e-05,
      "loss": 0.0463,
      "step": 110
    },
    {
      "epoch": 73.33,
      "eval_loss": 1.2258118391036987,
      "eval_runtime": 0.871,
      "eval_samples_per_second": 6.888,
      "eval_steps_per_second": 3.444,
      "step": 110
    },
    {
      "epoch": 74.0,
      "learning_rate": 3.591243860149759e-05,
      "loss": 0.0995,
      "step": 111
    },
    {
      "epoch": 74.67,
      "learning_rate": 3.4206127406028745e-05,
      "loss": 0.093,
      "step": 112
    },
    {
      "epoch": 75.0,
      "learning_rate": 3.253294540679257e-05,
      "loss": 0.0489,
      "step": 113
    },
    {
      "epoch": 76.0,
      "learning_rate": 3.089373510131354e-05,
      "loss": 0.1373,
      "step": 114
    },
    {
      "epoch": 77.0,
      "learning_rate": 2.9289321881345254e-05,
      "loss": 0.1337,
      "step": 115
    },
    {
      "epoch": 77.33,
      "learning_rate": 2.7720513617260856e-05,
      "loss": 0.0413,
      "step": 116
    },
    {
      "epoch": 78.0,
      "learning_rate": 2.6188100251265945e-05,
      "loss": 0.0911,
      "step": 117
    },
    {
      "epoch": 78.67,
      "learning_rate": 2.4692853399638917e-05,
      "loss": 0.0871,
      "step": 118
    },
    {
      "epoch": 79.0,
      "learning_rate": 2.323552596419889e-05,
      "loss": 0.0424,
      "step": 119
    },
    {
      "epoch": 80.0,
      "learning_rate": 2.181685175319702e-05,
      "loss": 0.127,
      "step": 120
    },
    {
      "epoch": 80.0,
      "eval_loss": 1.2826638221740723,
      "eval_runtime": 0.8716,
      "eval_samples_per_second": 6.884,
      "eval_steps_per_second": 3.442,
      "step": 120
    },
    {
      "epoch": 81.0,
      "learning_rate": 2.043754511182191e-05,
      "loss": 0.124,
      "step": 121
    },
    {
      "epoch": 81.33,
      "learning_rate": 1.9098300562505266e-05,
      "loss": 0.0409,
      "step": 122
    },
    {
      "epoch": 82.0,
      "learning_rate": 1.7799792455209018e-05,
      "loss": 0.0819,
      "step": 123
    },
    {
      "epoch": 82.67,
      "learning_rate": 1.6542674627869737e-05,
      "loss": 0.0816,
      "step": 124
    },
    {
      "epoch": 83.0,
      "learning_rate": 1.5327580077171587e-05,
      "loss": 0.0397,
      "step": 125
    },
    {
      "epoch": 84.0,
      "learning_rate": 1.415512063981339e-05,
      "loss": 0.1216,
      "step": 126
    },
    {
      "epoch": 85.0,
      "learning_rate": 1.3025886684430467e-05,
      "loss": 0.1204,
      "step": 127
    },
    {
      "epoch": 85.33,
      "learning_rate": 1.19404468143262e-05,
      "loss": 0.041,
      "step": 128
    },
    {
      "epoch": 86.0,
      "learning_rate": 1.0899347581163221e-05,
      "loss": 0.0772,
      "step": 129
    },
    {
      "epoch": 86.67,
      "learning_rate": 9.903113209758096e-06,
      "loss": 0.0779,
      "step": 130
    },
    {
      "epoch": 86.67,
      "eval_loss": 1.3157517910003662,
      "eval_runtime": 0.8712,
      "eval_samples_per_second": 6.887,
      "eval_steps_per_second": 3.444,
      "step": 130
    },
    {
      "epoch": 87.0,
      "learning_rate": 8.952245334118414e-06,
      "loss": 0.0401,
      "step": 131
    },
    {
      "epoch": 88.0,
      "learning_rate": 8.047222744854943e-06,
      "loss": 0.1173,
      "step": 132
    },
    {
      "epoch": 89.0,
      "learning_rate": 7.1885011480961164e-06,
      "loss": 0.1178,
      "step": 133
    },
    {
      "epoch": 89.33,
      "learning_rate": 6.37651293602628e-06,
      "loss": 0.0397,
      "step": 134
    },
    {
      "epoch": 90.0,
      "learning_rate": 5.611666969163243e-06,
      "loss": 0.079,
      "step": 135
    },
    {
      "epoch": 90.67,
      "learning_rate": 4.8943483704846475e-06,
      "loss": 0.0766,
      "step": 136
    },
    {
      "epoch": 91.0,
      "learning_rate": 4.224918331506955e-06,
      "loss": 0.0397,
      "step": 137
    },
    {
      "epoch": 92.0,
      "learning_rate": 3.6037139304146762e-06,
      "loss": 0.1141,
      "step": 138
    },
    {
      "epoch": 93.0,
      "learning_rate": 3.0310479623313127e-06,
      "loss": 0.1184,
      "step": 139
    },
    {
      "epoch": 93.33,
      "learning_rate": 2.5072087818176382e-06,
      "loss": 0.0386,
      "step": 140
    },
    {
      "epoch": 93.33,
      "eval_loss": 1.331322431564331,
      "eval_runtime": 0.873,
      "eval_samples_per_second": 6.873,
      "eval_steps_per_second": 3.436,
      "step": 140
    }
  ],
  "logging_steps": 1,
  "max_steps": 150,
  "num_train_epochs": 150,
  "save_steps": 20,
  "total_flos": 9.203523552018432e+16,
  "trial_name": null,
  "trial_params": null
}